© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15478
    Prev
    Next
    INDEX
    Explanations

    text related to military operations or equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific code or designation, likely related to military or defense items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bell
    -0.83
     contagious
    -0.73
     scandal
    -0.71
     revol
    -0.69
     memor
    -0.67
    agogue
    -0.66
     pneumonia
    -0.64
     smoking
    -0.63
     pneum
    -0.62
     circ
    -0.62
    POSITIVE LOGITS
    DF
    4.42
    df
    1.98
     DF
    1.61
    DS
    1.60
    DP
    1.59
    TF
    1.56
    DC
    1.48
    DM
    1.41
    FD
    1.40
    DL
    1.39
    Activations Density 0.013%

    No Known Activations